Clay

Name: Clay
Author: clay-inc

Local

github.com/clay-incCommunication36Updated 15w ago

Repository

About Clay

Clay (Mesh) MCP server lets AI clients search contacts, interactions, notes and events in the user's Mesh account. It also supports adding contacts, saving notes and managing groups. It suits users who want to query their personal network from an AI assistant.

Key features

01Search contacts by title, company or location
02Retrieve past interactions
03Contact statistics and percentages
04Add contacts and contact notes
05Create and update groups, query notes and events

Use cases

01Finding contacts who work at a given company
02Reviewing notes and interactions from a past period
03Adding follow-up notes to contacts or organizing them into groups

MCP support

The project is a remote MCP server reached at https://mcp.me.sh/mcp, connected via OAuth. The README names ChatGPT, Claude and Smithery as supported clients.

#contacts #crm #productivity

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config

{
  "mcpServers": {
    "clay": {
      "command": "npx",
      "args": [
        "-y",
        "@clayhq/clay-mcp"
      ],
      "env": {
        "CLAY_API_KEY": "<CLAY_API_KEY>"
      }
    }
  }
}

Run commandnpx -y @clayhq/clay-mcp

Environment variables to set

CLAY_API_KEYSecret

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages

npm@clayhq/clay-mcpstdio

Tools

Saved tool list · updated 3w ago

Parameter	Type	Required	Description
job_title	array	No	If the query refers to a job title, position, or industry, list relevant job titles as they would be on a LinkedIn profile. Examples: Developer should return positions such as 'Software Engineer', 'Full Stack Developer', 'Data Scientist', etc. Banker should return positions such as 'Financial Analyst', 'Investment Banker', 'Credit Analyst', etc. Healthcare industry should return positions such as 'Registered Nurse', 'Physician', 'Medical Director', etc. Legal industry should return positions such as 'Attorney', 'Legal Counsel', 'Paralegal', etc.
company_name	array	No	If the query refers to a company or acronym of companies, list company names as they would on a LinkedIn profile.
location	array	No	If the query refers to a location (city, state, country, region) where people are located or based, list the locations as they would appear on a LinkedIn profile. For example, if someone asks about "people in New York", return "New York City Metropolitan Area" or if they ask about "contacts in California", return "San Francisco Bay Area", "Greater Los Angeles Area", etc.
query	string	Yes	The raw search query from the user. Must preserve exact intent and details to enable accurate searching, including: relationship qualifiers, interaction metrics, relationship strength, names, companies, locations, dates (specific dates, date ranges, or relative dates like "last week" are required if mentioned by user), job titles, skills, and logical conditions (OR/AND).
keywords	array	No	Extract and list specific keywords related to professional expertise, skills, interests, or hobbies that the user is searching for. For example, if someone asks for 'people who know about machine learning or play tennis', the keywords would be ['machine learning', 'tennis']. Do not include job titles or company names here as those have dedicated fields. Focus on capturing domain expertise, technical skills, personal interests, and hobby-related terms that help identify relevant contacts.
limit	number	No	The number of contacts to return if the user asks for an amount.
exclude_contact_ids	array	No	Used to exclude previously returned contact IDs when the user asks for more results (e.g. "who else" or "show me more"). You should pass all contact IDs from previous searchContacts responses to ensure new results are shown.
sort_instructions	string	No	How would you like the results sorted? For example: "most recent contacts" will sort by last interaction date, "closest connections" will sort by interaction count, and "alphabetical" will sort by name. If no sort preference is given, this can be left empty.

Details

From the project README

Mesh MCP Server

A simple Model Context Protocol (MCP) server for Mesh.

Demo Video

Getting Started

Via Mesh (Preferred)

Visit Settings > Integrations > MCP Server for one-click connections to ChatGPT, Claude, and Smithery.
Followed the guided login flow to connect your account.

Custom

Tell your favorite agent or bot to connect https://mcp.me.sh/mcp via OAuth.

Features

Contact Search: Find contacts by job title, company, location, or specific keywords.
Interaction Search: Retrieve past interactions based on various criteria.
Contact Statistics: Obtain numerical statistics and percentages related to your contacts.
Detailed Contact Info: Access comprehensive information for a specific contact by ID.
Add New Contact: Create new contacts with details like name, phone, email, and more.
Add Contact Note: Create a note associated with a specific contact.
Retrieve Groups: Get all user-defined groups or lists.
Create New Group: Create a new group or list.
Update Group: Update a group's title or modify its members.
Retrieve Notes: Get notes created within a specified date range.
Retrieve Events: Fetch meetings and events scheduled within a specified date range.

Examples

"Who in my network works at Google as a Product Manager?"
"Who have I emailed the most this year?"
"How many of my contacts are based in New York?"
"Who is John Smith?"
"Add a new contact named Jane Doe, who is a Designer at Figma."
"Save a note for John Smith: 'Follow up about the Q2 report.'"
"Create a group called 'Investors 2025.'"
"Add Jane Doe and John Smith to the Investors 2025 group."
"What notes did I take last week?"
"What meetings do I have scheduled for tomorrow?"

More information

Learn more and reach out at the Mesh Library.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

Read the getting-started guide

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.